© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 47631
    Prev
    Next
    INDEX
    Explanations

    questions about actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .).
    -0.08
    ä¹ĭæīĢ以
    -0.07
     zwar
    -0.07
    å¹¶éĿŀ
    -0.07
    ').
    -0.07
     "").
    -0.07
    èϽ
    -0.07
     âĤ¬**
    -0.06
    **.
    -0.06
    ...).
    -0.06
    POSITIVE LOGITS
    ï¼Ł
    0.20
    ØŁ
    0.19
    ï¼Ł”
    0.18
    ï¼ŁãĢį
    0.17
    ï¼Łï¼ī
    0.17
    ()?
    0.16
    ?</
    0.16
    ï¼Ł**
    0.16
    çļĦåij¢
    0.16
    }?
    0.16
    Activations Density 1.248%

    No Known Activations